{"as_of":"2026-08-08T18:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c15839a7b7efeb5e6d0ad0ce833c406413af5c4c691d8f8fef534118e2adfdbc","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:35:34.323405Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-07T15:35:36.417779Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2010.11723","last_updated":"2020-11-23T16:07:38Z","snapshot_observed_at":"2026-08-02T15:36:40.412954Z","submitted_at":"2020-10-17T04:18:04Z","title":"Learning from Suboptimal Demonstration via Self-Supervised Reward Regression","version":3},"cited_work":{"arxiv_id":"2010.11723","doi":null,"metadata_source":"pith","pith_arxiv_id":"2010.11723","snapshot_observed_at":"2026-08-07T15:35:36.417779Z","title":"Learning from Suboptimal Demonstration via Self-Supervised Reward Regression","venue":"cs.RO","work_id":"f3b29f29-599c-430f-b104-99d3cd3fc2b6","year":2020},"citing_paper":{"arxiv_id":"2505.14820","last_updated":"2025-05-25T16:55:31Z","snapshot_observed_at":"2026-08-07T15:26:49.397007Z","submitted_at":"2025-05-20T18:36:52Z","title":"Imitation Learning via Focused Satisficing","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T15:35:34.323405Z"},"links":{"cited_paper":"/paper/2010.11723","citing_paper":"/paper/2505.14820"},"observation_digest":"sha256:de81a743b9f55096d9887ace0e3289128af4cbd45d8233dbb8688537217d6fc5","observation_id":"c42fc5e4-aa07-442b-b18b-e99483566b8a","resolution":{"observed_at":"2026-08-07T15:35:36.506393Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11723","last_updated":"2020-11-23T16:07:38Z","snapshot_observed_at":"2026-08-02T15:36:40.412954Z","submitted_at":"2020-10-17T04:18:04Z","title":"Learning from Suboptimal Demonstration via Self-Supervised Reward Regression","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11723","snapshot_observed_at":"2026-08-04T10:24:56.563390Z","title":"Learning from Sub- optimal Demonstration via Self-Supervised Reward Regression,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2510.09976","last_updated":"2026-06-25T14:25:12Z","snapshot_observed_at":"2026-08-04T10:24:54.103532Z","submitted_at":"2025-10-11T03:11:18Z","title":"Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T10:24:56.563390Z"},"links":{"cited_paper":"/paper/2010.11723","citing_paper":"/paper/2510.09976"},"observation_digest":"sha256:c442e11e599a1c50c48c3b8bfe9ce3de7c0a99f0fee56fd1ba9833fd0d216350","observation_id":"6fbbfd92-83c1-4d5f-8f4e-ead239477dac","resolution":{"observed_at":"2026-08-04T10:24:56.563390Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2010.11723/citation-record","integrity":"/paper/2010.11723/integrity","json":"/paper/2010.11723/citation-record.json","paper":"/paper/2010.11723"},"outbound":[],"paper":{"arxiv_id":"2010.11723","last_updated":"2020-11-23T16:07:38Z","latest_version":3,"primary_category":"cs.RO","snapshot_observed_at":"2026-08-02T15:36:40.412954Z","submitted_at":"2020-10-17T04:18:04Z","title":"Learning from Suboptimal Demonstration via Self-Supervised Reward Regression"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2010.11723."}